Student emotional feature and difficulty adaptability evaluation method and device and medium
Through deep learning technology, students' multimodal data are analyzed, students' emotional characteristics and learning difficulty adaptability are evaluated, and the problem of difficulty difficulty is difficult to achieve personalized teaching in the existing technology is solved, and efficient subject preference and difficulty adaptability assessment is achieved, which improves teaching quality and learning satisfaction.
Patent Information
- Application Number
- CN202411719150.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-27
- Publication Date
- 2025-03-18
AI Technical Summary
The existing technology is difficult to achieve personalized teaching, and it is impossible to effectively evaluate students' emotional characteristics and difficulty adaptability, resulting in low educational quality and learning satisfaction.
By obtaining students' multimodal data (text data and image data), using deep learning technologies such as Beart word vector model, LSTM model, CNN model and Transformer model, students' emotional characteristics and image features are extracted, and feature aggregation and adaptability assessment are carried out to generate subject preferences, difficulty adaptability assessment results and personalized learning suggestions.
A comprehensive assessment of students' emotional characteristics and learning difficulty adaptability is achieved, personalized learning suggestions and educational adjustments are provided, teaching effectiveness and learning satisfaction are improved, and personalized teaching is achieved.
Smart Images
Figure CN119648489A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of Internet technology, and in particular to a method, device and medium for evaluating students' emotional characteristics and difficulty adaptability. Background Art
[0002] With the changes of the times, the continuous progress of educational concepts and the rapid development of science and technology, personalized teaching has changed from an idealized educational model to a broad consensus in the field of education. More and more educators realize that every student has a unique personality, interest and potential. Therefore, education should no longer be a "one-size-fits-all" mass production, but should pay more attention to teaching students in accordance with their aptitude and fully tapping and giving full play to the individual characteristics of each student.
[0003] In this context, personalized teaching has gradually become an important way to improve the quality of education and cultivate innovative talents, and has been highly valued and widely promoted by the education community.
[0004] Therefore, how to achieve personalized teaching for different individual students becomes a problem that needs to be solved. Summary of the invention
[0005] The technical problem to be solved by this application is to provide a method, device and medium for evaluating students' emotional characteristics and difficulty adaptability in view of the above-mentioned deficiencies in the prior art, so as to solve the problems existing in the prior art.
[0006] In a first aspect, the present application provides a method for evaluating students' emotional characteristics and difficulty adaptability, the method comprising:
[0007] S1. Acquire multimodal data of students, where the multimodal data includes text data and image data;
[0008] S2, determining corresponding emotional features according to the text data;
[0009] S3, obtaining corresponding image features according to the image data;
[0010] S4. Perform an adaptability assessment based on the emotional features and the image features to obtain the student's subject preference, difficulty adaptability assessment results and personalized learning suggestions.
[0011] In some embodiments, S2 includes:
[0012] The text data is converted into word vector data by using the Beart word vector model;
[0013] The word vector data is input into a pre-trained long short-term memory network LSTM model to obtain the students' sentiment labels in each subject.
[0014] In some embodiments, S3 includes:
[0015] The image data is subjected to image feature extraction through a convolutional neural network (CNN) model to obtain corresponding image features.
[0016] In some embodiments, S4 includes:
[0017] Performing feature aggregation on the emotion feature and the image feature to obtain aggregated feature data;
[0018] The aggregated feature data is adaptively evaluated through an evaluation model to obtain the student's subject preference, difficulty adaptability evaluation results and personalized learning suggestions.
[0019] In some embodiments, the aggregated feature data is adaptively evaluated by an evaluation model to obtain the student's subject preference, difficulty adaptability evaluation results and personalized learning suggestions, including:
[0020] Performing deep learning on the aggregated feature data through Transformer, and performing feature dimensionality reduction processing through principal component analysis (PCA) to obtain reduced-dimensional feature data;
[0021] Based on the reduced dimension feature data, an adaptability assessment is performed through an assessment model to obtain the student's subject preference, difficulty adaptability assessment results and personalized learning suggestions.
[0022] In some embodiments, it also includes:
[0023] The Adam optimization algorithm is used to update the model parameters.
[0024] In some embodiments, the student's subject preference, difficulty adaptability assessment results, and personalized learning suggestions specifically include:
[0025] Student-level adaptability to subject difficulty, learning interest, learning motivation, and learning pressure;
[0026] Teaching style, teaching effectiveness, and teaching satisfaction at the teacher level;
[0027] Subject difficulty, subject interest, and subject learning effect at the subject level;
[0028] Learning paths, learning resources and teaching methods in students’ personalized learning recommendations;
[0029] Teaching suggestions and training in teacher teaching improvement proposals;
[0030] The subject resource allocation recommendations include curriculum adjustment, teacher allocation adjustment and teaching resource allocation adjustment.
[0031] In a second aspect, the present application provides a device for evaluating student emotional characteristics and difficulty adaptability, the device comprising:
[0032] A data acquisition module, configured to acquire multimodal data of students, wherein the multimodal data includes text data and image data;
[0033] An emotional feature determination module, configured to determine corresponding emotional features according to the text data;
[0034] An image feature acquisition module, configured to obtain corresponding image features according to the image data;
[0035] The adaptability assessment module is configured to perform adaptability assessment based on the emotional features and the image features to obtain the student's subject preference, difficulty adaptability assessment results and personalized learning suggestions.
[0036] In a third aspect, the present application provides a device for evaluating students' emotional characteristics and difficulty adaptability, comprising a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to implement the method for evaluating students' emotional characteristics and difficulty adaptability described in the first aspect above.
[0037] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method for evaluating students' emotional characteristics and difficulty adaptability described in the first aspect above is implemented.
[0038] The present application provides a method, device and medium for evaluating the emotional characteristics and difficulty adaptability of students, the method comprising: obtaining multimodal data of students, the multimodal data comprising text data and image data; determining corresponding emotional characteristics according to the text data; obtaining corresponding image features according to the image data; performing adaptability evaluation according to the emotional characteristics and the image features, and obtaining the subject preference, difficulty adaptability evaluation results and personalized learning suggestions of the students. The present application proposes a method for evaluating the emotional characteristics and difficulty adaptability of students based on subject interests, which comprehensively evaluates the emotional characteristics and learning difficulty adaptability of students for different subjects through multimodal data (including students' daily learning data and classroom image data) combined with advanced deep learning technology, and generates the final evaluation results through data collection, data processing, emotional label generation, feature extraction, feature aggregation, model training and evaluation, and provides students with personalized learning suggestions and educational adjustments. The method for evaluating the emotional characteristics and difficulty adaptability of students based on subject interests in the present application can meet the personalized learning needs of different students, improve teaching effects and learning satisfaction, and realize personalized teaching of different individual students, thereby helping to improve teaching quality. BRIEF DESCRIPTION OF THE DRAWINGS
[0039] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.
[0040] Figure 1 A flow chart of a method for evaluating student emotional characteristics and difficulty adaptability provided in an embodiment of the present application;
[0041] Figure 2 A flowchart of another method for evaluating student emotional characteristics and difficulty adaptability provided in an embodiment of the present application;
[0042] Figure 3 A schematic diagram of the structure of a device for evaluating student emotional characteristics and difficulty adaptability provided in an embodiment of the present application;
[0043] Figure 4 A schematic diagram of the structure of another device for evaluating students' emotional characteristics and difficulty adaptability provided in an embodiment of the present application.
[0044] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION
[0045] In order to enable those skilled in the art to better understand the technical solution of the present application, the implementation mode of the present application will be further described in detail below with reference to the accompanying drawings.
[0046] It should be understood that the specific embodiments and drawings described herein are only used to explain the present application, rather than to limit the present application.
[0047] It can be understood that, in the absence of conflict, the various embodiments in the present application and the various features in the embodiments can be combined with each other.
[0048] It can be understood that, for the convenience of description, the drawings of the present application only show the parts related to the present application, while the parts unrelated to the present application are not shown in the drawings.
[0049] It can be understood that each unit and module involved in the embodiments of the present application may correspond to only one physical structure, or may be composed of multiple physical structures, or multiple units and modules may be integrated into one physical structure.
[0050] It can be understood that the terms "first", "second", etc. in the embodiments of the present application are used to distinguish different objects, or to distinguish different processing of the same object, rather than to describe a specific order of objects.
[0051] It is understandable that, in the absence of conflict, the functions and steps marked in the flowcharts and block diagrams of the present application may occur in an order different from that marked in the drawings.
[0052] It is understood that the flowcharts and block diagrams of the present application illustrate the possible architectures, functions, and operations of the systems, devices, equipment, and methods according to the various embodiments of the present application. Among them, each box in the flowchart or block diagram may represent a unit, module, program segment, code, which contains executable instructions for implementing the specified functions. Moreover, each box or combination of boxes in the block diagram and flowchart may be implemented by a hardware-based system that implements the specified functions, or by a combination of hardware and computer instructions.
[0053] It can be understood that the units and modules involved in the embodiments of the present application can be implemented by software or hardware, for example, the units and modules can be located in a processor.
[0054] In order to comprehensively evaluate students' emotional characteristics and adaptability to learning difficulty for different subjects, and ultimately provide students with personalized learning suggestions and educational adjustments, this application proposes a method for evaluating students' emotional characteristics and adaptability to difficulty based on subject interests. Through multimodal data (including students' daily learning data and classroom image data) combined with advanced deep learning technology, students' emotional characteristics and adaptability to learning difficulty for different subjects are comprehensively evaluated. The evaluation generates the final evaluation results through data collection, data processing, emotional label generation, feature extraction, feature aggregation, model training and evaluation, and provides students with personalized learning suggestions and educational adjustments. The method for evaluating students' emotional characteristics and adaptability to difficulty based on subject interests in this application can meet the personalized learning needs of different students, improve teaching effectiveness and learning satisfaction, and realize personalized teaching for different individual students, thereby helping to improve teaching quality.
[0055] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.
[0056] The present application provides a method for evaluating students' emotional characteristics and difficulty adaptability. The working process of the method can be implemented by electronic devices, such as computers, handheld smart terminals, etc. For the convenience of explanation, the embodiments of the present application are described with the method execution subject being a computer.
[0057] Figure 1A schematic diagram of a method for evaluating student emotional characteristics and difficulty adaptability provided in an embodiment of the present application, Figure 2 Another schematic diagram of the method for evaluating student emotional characteristics and difficulty adaptability provided in the embodiment of the present application is as follows: Figure 1 as well as Figure 2 As shown, the present application provides a method for evaluating students' emotional characteristics and difficulty adaptability, the method comprising S1-S4, specifically as follows:
[0058] S1. Acquire multimodal data of students, where the multimodal data includes text data and image data;
[0059] Specifically, text data includes students’ text learning logs (including homework, class discussion records, etc.). Image data includes classroom image data (such as students’ expressions and interactions during class). By building an effective data collection platform, students’ learning logs and classroom image data can be obtained in real time.
[0060] By acquiring data, we can provide basic data for subsequent analysis and ensure the comprehensiveness and accuracy of the data.
[0061] S2, determining corresponding emotional features according to the text data;
[0062] In some embodiments, S2 includes:
[0063] The text data is converted into word vector data by using the Beart word vector model;
[0064] The word vector data is input into a pre-trained long short-term memory network LSTM model to obtain the students' sentiment labels in each subject.
[0065] Specifically, by deploying the Beart word vector model and corresponding text processing tools, the input is the original learning log data, and the output is the processed word vector data. The specific processing process is to use the Beart word vector model to convert the student log into a high-dimensional vector form. The mathematical formula is as follows:
[0066] Embedding(word)→Vector
[0067] By converting each word into a vector form, the semantic information can be converted into a format that can be processed by a deep learning model for subsequent model input.
[0068] After obtaining the word vector data, an LSTM model is built for sequence modeling. The input is the word vector data, and the output is the student's emotional label in each subject (such as positive, negative, neutral). The specific processing process is to use the LSTM network for training to identify emotional features, output the emotional category through the Softmax function, and accurately identify the student's emotions to provide annotation information for subsequent analysis.
[0069] S3, obtaining corresponding image features according to the image data;
[0070] In some embodiments, S3 includes:
[0071] The image data is subjected to image feature extraction through a convolutional neural network (CNN) model to obtain corresponding image features.
[0072] Specifically, the image feature extraction is performed by establishing a CNN model, the input is the collected classroom image data, and the output is the high-representation feature data obtained after convolution. The processing process is to use CNN to extract image features, and the basic formula is:
[0073] Y = f(X) = CNN(X)
[0074] Among them, X is the input image data, and Y is the extracted feature representation. By extracting visual features that can reflect the emotional state of students, multi-dimensional data can be provided for subsequent aggregation.
[0075] S4. Perform an adaptability assessment based on the emotional features and the image features to obtain the student's subject preference, difficulty adaptability assessment results and personalized learning suggestions.
[0076] In some embodiments, S4 includes:
[0077] Performing feature aggregation on the emotion feature and the image feature to obtain aggregated feature data;
[0078] The aggregated feature data is adaptively evaluated through an evaluation model to obtain the student's subject preference, difficulty adaptability evaluation results and personalized learning suggestions.
[0079] Specifically, the processed emotion labels and image feature data are first merged, the input is the emotion label and the high-representation feature data, and the output is the aggregated feature data. The processing process is to merge the emotion label and the image feature to form a new feature matrix:
[0080] Z=Concatenate(E,Y)
[0081] Among them, Z is the aggregate feature data, E is the emotional feature, and Y is the image feature data. By merging data from different sources, the interpretability and accuracy of the model are enhanced.
[0082] In some embodiments, the aggregated feature data is adaptively evaluated by an evaluation model to obtain the student's subject preference, difficulty adaptability evaluation results and personalized learning suggestions, including:
[0083] Performing deep learning on the aggregated feature data through Transformer, and performing feature dimensionality reduction processing through principal component analysis (PCA) to obtain reduced-dimensional feature data;
[0084] Based on the reduced dimension feature data, an adaptability assessment is performed through an assessment model to obtain the student's subject preference, difficulty adaptability assessment results and personalized learning suggestions.
[0085] In some embodiments, it also includes: using the Adam optimization algorithm to update the model parameters.
[0086] Specifically, we built the Transformer framework, PCA dimensionality reduction, and Adam optimization algorithm environment. The input is aggregated feature data, and the output is the feature representation after dimensionality reduction and the trained evaluation model. The processing includes: applying Transformer to perform deep learning on aggregated features; using PCA to perform feature dimensionality reduction; and using the Adam optimization algorithm to update model parameters. Through multi-level learning, the model can effectively capture the students' adaptive characteristics and improve prediction accuracy.
[0087] In some embodiments, the student's subject preference, difficulty adaptability assessment results, and personalized learning suggestions specifically include:
[0088] Student-level adaptability to subject difficulty, learning interest, learning motivation, and learning pressure;
[0089] Teaching style, teaching effectiveness, and teaching satisfaction at the teacher level;
[0090] Subject difficulty, subject interest, and subject learning effect at the subject level;
[0091] Learning paths, learning resources and teaching methods in students’ personalized learning recommendations;
[0092] Teaching suggestions and training in teacher teaching improvement proposals;
[0093] The subject resource allocation recommendations include curriculum adjustment, teacher allocation adjustment and teaching resource allocation adjustment.
[0094] Specifically, we use Q-learning to optimize strategies, and obtain students’ preferences in various subjects, difficulty adaptability assessment results, and personalized learning suggestions based on the feature data after dimensionality reduction. We optimize students’ learning methods and strategies through dynamic learning and improve the overall learning effect.
[0095] The following is a detailed example of the technical solution of this application:
[0096] Example 1:
[0097] The school’s academic affairs department hopes to use students’ emotional characteristics and difficulty adaptability assessment methods based on subject interests to optimize resource allocation, improve educational efficiency, and promote educational equity.
[0098] Application Process:
[0099] 1. Data Collection:
[0100] Student data: collect students’ academic performance, study time, learning behavior data (such as homework completion, class participation, etc.) in various subjects, and student psychological assessment data.
[0101] Teacher data: Collect data on teachers’ teaching experience, teaching style, teaching evaluation, etc.
[0102] Subject data: collect data such as the syllabus, teaching content, and teaching objectives of each subject.
[0103] 2. Data processing:
[0104] Clean, annotate and format the collected data, such as converting text data into word vectors and image data into feature vectors.
[0105] 3. Model training:
[0106] Using deep learning techniques, LSTM, CNN and Transformer, the processed data is trained to learn students’ emotional characteristics, adaptability to learning difficulty and teachers’ teaching styles.
[0107] 4. Evaluation indicators:
[0108] Student level: adaptability to subject difficulty, learning interest, learning motivation, learning pressure, etc.
[0109] Teacher level: teaching style, teaching effectiveness, teaching satisfaction, etc.
[0110] Subject level: subject difficulty, subject interest, subject learning effect, etc.
[0111] 5. Evaluation direction:
[0112] Personalized learning for students: Based on the students’ assessment results, we recommend appropriate learning paths, learning resources, and teaching methods. For example, we recommend more interesting learning content and tutoring materials for students with low learning interest and high learning pressure.
[0113] Teacher teaching improvement: Provide targeted teaching suggestions and training based on teacher evaluation results, such as providing information-based teaching training for teachers whose teaching style is too traditional, and providing teaching skills training for teachers with poor teaching results.
[0114] Subject resource allocation: According to the evaluation results of the subject, adjust the curriculum setting, teacher allocation and teaching resource allocation, such as adding subject courses that students are interested in and assigning experienced teachers to subjects that are more difficult to learn.
[0115] 6. Evaluation process:
[0116] Regular evaluation: Regularly evaluate students, teachers and subjects to understand teaching status and learning outcomes in a timely manner.
[0117] Dynamic adjustment: Based on the evaluation results, dynamically adjust teaching strategies and resource allocation to ensure the effective use of educational resources.
[0118] Continuous improvement: Continuously improve the assessment model and assessment methods to improve the accuracy and effectiveness of the assessment.
[0119] Expected results:
[0120] Improve the efficiency of educational resource utilization: optimize resource allocation through accurate assessment, avoid resource waste and improve educational efficiency.
[0121] Promote educational equity: Provide personalized learning support for different students, narrow the learning gap, and promote educational equity.
[0122] Improve the quality of education: Improve the quality of education by improving teaching methods and teaching strategies, improving teachers' teaching level and students' learning outcomes.
[0123] The following are other actual sample examples of the technical solution of this application:
[0124] Example 2:
[0125] In a middle school mathematics class, we collected learning logs and classroom interaction images of 30 students. After data processing and model training, we found that most students tended to have negative emotional labels for mathematics. The results guided teachers to improve classroom interaction and participation mechanisms, ultimately improving students' learning interest and engagement.
[0126] Example 3:
[0127] In an online English learning course, the learning behavior and image data of 100 students were collected. After evaluation, it was found that some students had low emotional labels in English writing. Based on this, it was recommended that teachers provide more targeted feedback and materials, which significantly improved students' learning performance and enthusiasm.
[0128] The analysis of these embodiments demonstrates the effectiveness and guidance of this technical solution for educational practice, and realizes data-driven personalized education.
[0129] Example 4:
[0130] A school found through evaluation that students generally had low interest in learning physics and poor adaptability to learning difficulty. Based on the evaluation results, the school adjusted the teaching content and teaching methods of physics, added experimental and interactive sessions, and provided students with more learning resources. After a period of time, students' physics learning performance and interest have improved significantly.
[0131] Example 5:
[0132] A school found through evaluation that some teachers’ teaching styles were too traditional and their teaching results were poor. Based on the evaluation results, the school provided these teachers with information-based teaching training to help them master more advanced teaching methods and teaching tools. After a period of time, the teachers’ teaching results and students’ academic performance improved significantly.
[0133] Through the above examples, the student emotional characteristics and difficulty adaptability assessment method based on subject preferences provided by this application can help the school's academic affairs department optimize resource allocation, improve educational efficiency, and promote educational equity. The application of this method needs to be combined with the actual situation of the school and personalized design and implementation to achieve the best results.
[0134] This application proposes a method for evaluating students' emotional characteristics and difficulty adaptability based on subject interests. Through multimodal data (including students' daily learning data and classroom image data) combined with advanced deep learning technology, students' emotional characteristics and learning difficulty adaptability for different subjects are comprehensively evaluated. The evaluation generates the final evaluation results through data collection, data processing, emotional label generation, feature extraction, feature aggregation, model training and evaluation, providing students with personalized learning suggestions and educational adjustments. This application's method for evaluating students' emotional characteristics and difficulty adaptability based on subject interests can meet the personalized learning needs of different students, improve teaching effectiveness and learning satisfaction, and realize personalized teaching for different individual students, thereby helping to improve teaching quality.
[0135] It should be understood that, although the various steps in the flowcharts in the above-described embodiments are sequentially displayed according to the indications of the arrows, these steps are not necessarily executed sequentially in the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps is not strictly limited in order, and they can be executed in other orders. Moreover, at least a portion of the steps in the figure may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily to be carried out sequentially, but can be executed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.
[0136] Figure 3 A schematic diagram of a device for evaluating student emotional characteristics and difficulty adaptability provided in an embodiment of the present application is shown in FIG. Figure 3 As shown, the present application provides a device for evaluating student emotional characteristics and difficulty adaptability, the device comprising:
[0137] A data acquisition module 11, which is configured to acquire multimodal data of students, wherein the multimodal data includes text data and image data;
[0138] An emotional feature determination module 12, which is configured to determine corresponding emotional features according to the text data;
[0139] An image feature acquisition module 13, which is configured to obtain corresponding image features according to the image data;
[0140] The adaptability assessment module 14 is configured to perform adaptability assessment based on the emotional features and the image features to obtain the student's subject preference, difficulty adaptability assessment results and personalized learning suggestions.
[0141] Regarding the limitation of the device for evaluating the student's emotional characteristics and difficulty adaptability, reference may be made to the limitation of the method for evaluating the student's emotional characteristics and difficulty adaptability in the above-mentioned embodiments of the present application, which will not be elaborated in this embodiment.
[0142] Figure 4 Another schematic diagram of the device for evaluating student emotional characteristics and difficulty adaptability provided by the embodiment of the present application is as follows: Figure 4 As shown, in some embodiments, the present application provides a device for evaluating student emotional characteristics and difficulty adaptability, including a memory 22 and a processor 21, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the student emotional characteristics and difficulty adaptability evaluation method in the above-mentioned embodiments of the present application.
[0143] The memory is connected to the processor, the memory may be a flash memory or a read-only memory or other memory, and the processor may be a central processing unit or a single-chip microcomputer.
[0144] In some embodiments, the present application provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method for evaluating student emotional characteristics and difficulty adaptability in the above-mentioned embodiments of the present application is implemented.
[0145] The computer-readable storage medium includes volatile or non-volatile, removable or non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, computer program modules or other data). Computer-readable storage media include, but are not limited to, RAM (Random Access Memory), ROM (Read-Only Memory), EEPROM (Electrically Erasable Programmable read only memory), flash memory or other memory technology, CD-ROM (Compact Disc Read-Only Memory), digital versatile disk (DVD) or other optical disk storage, magnetic cassettes, magnetic tapes, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store the desired information and can be accessed by a computer.
[0146] It is to be understood that the above embodiments are merely exemplary embodiments used to illustrate the principles of the present application, but the present application is not limited thereto. For those skilled in the art, various modifications and improvements can be made without departing from the spirit and substance of the present application, and these modifications and improvements are also considered to be within the scope of protection of the present application.
Claims
1. A method for evaluating students' emotional characteristics and difficulty adaptability, characterized in that: The method comprises: S1. Acquire multimodal data of students, where the multimodal data includes text data and image data; S2, determining corresponding emotional features according to the text data; S3, obtaining corresponding image features according to the image data; S4. Perform an adaptability assessment based on the emotional features and the image features to obtain the student's subject preference, difficulty adaptability assessment results and personalized learning suggestions.
2. The method for evaluating students' emotional characteristics and difficulty adaptability according to claim 1, characterized in that: S2, including: The text data is converted into word vector data by using the Beart word vector model; The word vector data is input into a pre-trained long short-term memory network LSTM model to obtain the students' sentiment labels in each subject.
3. The method for evaluating students' emotional characteristics and difficulty adaptability according to claim 1, characterized in that: S3, including: The image data is subjected to image feature extraction through a convolutional neural network (CNN) model to obtain corresponding image features.
4. The method for evaluating students' emotional characteristics and difficulty adaptability according to claim 1 is characterized in that: S4, including: Performing feature aggregation on the emotion feature and the image feature to obtain aggregated feature data; The aggregated feature data is adaptively evaluated through an evaluation model to obtain the student's subject preference, difficulty adaptability evaluation results and personalized learning suggestions.
5. The method for evaluating students' emotional characteristics and difficulty adaptability according to claim 4 is characterized in that: The aggregated feature data is adaptively evaluated through an evaluation model to obtain the student's subject preference, difficulty adaptability evaluation results and personalized learning suggestions, including: Performing deep learning on the aggregated feature data through Transformer, and performing feature dimensionality reduction processing through principal component analysis (PCA) to obtain reduced-dimensional feature data; Based on the reduced dimension feature data, an adaptability assessment is performed through an assessment model to obtain the student's subject preference, difficulty adaptability assessment results and personalized learning suggestions.
6. The method for evaluating students' emotional characteristics and difficulty adaptability according to claim 5 is characterized in that: Also includes: The Adam optimization algorithm is used to update the model parameters.
7. The method for evaluating students' emotional characteristics and difficulty adaptability according to any one of claims 1 to 6, characterized in that: The student’s subject preferences, difficulty adaptability assessment results and personalized learning suggestions include: Student-level adaptability to subject difficulty, learning interest, learning motivation, and learning pressure; Teaching style, teaching effectiveness, and teaching satisfaction at the teacher level; Subject difficulty, subject interest, and subject learning effect at the subject level; Learning paths, learning resources and teaching methods in students’ personalized learning recommendations; Teaching suggestions and training in teacher teaching improvement proposals; The subject resource allocation recommendations include curriculum adjustment, teacher allocation adjustment and teaching resource allocation adjustment.
8. A device for evaluating students' emotional characteristics and difficulty adaptability, characterized in that: The device comprises: A data acquisition module, configured to acquire multimodal data of students, wherein the multimodal data includes text data and image data; An emotional feature determination module, configured to determine corresponding emotional features according to the text data; An image feature acquisition module, configured to obtain corresponding image features according to the image data; The adaptability assessment module is configured to perform adaptability assessment based on the emotional features and the image features to obtain the student's subject preference, difficulty adaptability assessment results and personalized learning suggestions.
9. A device for evaluating students' emotional characteristics and difficulty adaptability, characterized in that: It comprises a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to implement the student emotional characteristics and difficulty adaptability assessment method as described in any one of claims 1-7.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for evaluating students' emotional characteristics and difficulty adaptability according to any one of claims 1 to 7 is implemented.